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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or researchers

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

    [@ Schneps]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MIDDLEWARE
    -0.42
     Kuan
    -0.39
    ńcu
    -0.37
     uni
    -0.37
     “
    -0.35
    .”
    -0.34
    DataMember
    -0.34
    i
    -0.33
    ethereum
    -0.32
     Bü
    -0.32
    POSITIVE LOGITS
    ps
    2.42
    PS
    2.08
     ps
    1.77
     PS
    1.77
     Ps
    1.44
    Ps
    1.33
    пс
    1.13
    psin
    1.13
    psa
    1.10
    pso
    1.08
    Act Density 0.015%

    No Known Activations