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

    Neuronpedia

    INDEX
    Explanations

    concentration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tween
    -0.07
     travelers
    -0.07
     failure
    -0.07
     interrupt
    -0.06
    .ReadAllText
    -0.06
     Greek
    -0.06
     Gas
    -0.06
    ROOM
    -0.06
     camera
    -0.06
     sunscreen
    -0.06
    POSITIVE LOGITS
    Personally
    0.07
    ')+
    0.06
     subsidiary
    0.06
    step
    0.06
     đảo
    0.06
     αγ
    0.06
     *)(
    0.06
    /File
    0.06
     hm
    0.06
    _sb
    0.06
    Act Density 0.018%

    No Known Activations