Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical interpolation methods and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    interpolation using models or frames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assertIs
    -0.41
    Side
    -0.39
    aim
    -0.38
    <h2>
    -0.38
    ']>
    -0.37
    äfts
    -0.36
    Daemon
    -0.35
    GrantedAuthority
    -0.35
     vå
    -0.34
    (&:
    -0.34
    POSITIVE LOGITS
     interpolation
    1.20
     Interpolation
    1.13
    interpolation
    1.09
    Interpolation
    1.01
    interpolate
    0.99
     interpolate
    0.94
     interpolated
    0.88
    polated
    0.83
     interpol
    0.83
    polate
    0.82
    Act Density 0.028%

    No Known Activations