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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    持有
    -0.07
    IDES
    -0.07
     allocate
    -0.07
    }
↵
↵
    -0.07
     haze
    -0.06
    Josh
    -0.06
    nano
    -0.06
    fgets
    -0.06
    indices
    -0.06
    锎
    -0.06
    POSITIVE LOGITS
    -reviewed
    0.07
    _ac
    0.07
    ^{
    0.06
     Patrol
    0.06
     cupboard
    0.06
    re
    0.06
     Guarantee
    0.06
    ------+------+
    0.06
     unanim
    0.06
     Enemy
    0.06
    Act Density 1.435%

    No Known Activations