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

    Neuronpedia

    INDEX
    Explanations

    expressions of comparison or relativity regarding quality and necessity

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

    whole square, already filmed, fully healthy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.79
     fashiola
    -0.78
    findpost
    -0.76
     imagui
    -0.74
     zwiſchen
    -0.73
    <unused8>
    -0.73
    <unused80>
    -0.73
    <unused74>
    -0.73
    [@BOS@]
    -0.73
    <unused3>
    -0.72
    POSITIVE LOGITS
    .
    0.33
    Re
    0.29
    ↵
    0.29
    口
    0.29
    ↵↵
    0.28
    …
    0.28
      
    0.27
    ..
    0.27
     <<<<<<<<<<<<<<
    0.26
    цездатний
    0.26
    Act Density 0.045%

    No Known Activations