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

    Neuronpedia

    INDEX
    Explanations

    Feelings and sensations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eleri
    -0.07
     lava
    -0.06
     Trader
    -0.06
     bred
    -0.06
    .servers
    -0.06
    _partner
    -0.06
     kanıt
    -0.06
    ratings
    -0.06
     inmate
    -0.06
     lifecycle
    -0.06
    POSITIVE LOGITS
    ashtra
    0.08
    aData
    0.07
     MediaType
    0.07
     Arg
    0.07
     лицо
    0.06
     cvs
    0.06
    .iter
    0.06
    nten
    0.06
    于是
    0.06
     =================================================================================
    0.06
    Act Density 0.137%

    No Known Activations