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

    Neuronpedia

    INDEX
    Explanations

    coming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atrix
    -0.07
    Humans
    -0.06
    UILTIN
    -0.06
     ads
    -0.06
     güvenlik
    -0.06
     knowledge
    -0.06
    _ES
    -0.06
     crian
    -0.06
     climax
    -0.06
     Tamb
    -0.06
    POSITIVE LOGITS
    ｭ
    0.07
    _increment
    0.07
    .band
    0.06
    _
    0.06
    /open
    0.06
    ै,
    0.06
    REFER
    0.06
     subscribed
    0.06
    _course
    0.06
    boss
    0.06
    Act Density 0.247%

    No Known Activations