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

    Neuronpedia

    INDEX
    Explanations

    simple passwords

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เพชร
    -0.07
     Tottenham
    -0.07
    sov
    -0.07
     Installing
    -0.07
     upscale
    -0.07
     Fighters
    -0.07
     "***
    -0.07
     spoken
    -0.07
     chords
    -0.07
     Belfast
    -0.07
    POSITIVE LOGITS
    החלטת
    0.07
    切断
    0.07
    地理
    0.06
    (bit
    0.06
    <File
    0.06
    _rx
    0.06
    vey
    0.06
    尢
    0.06
    _QMARK
    0.06
     CAN
    0.06
    Act Density 0.005%

    No Known Activations