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

    Neuronpedia

    INDEX
    Explanations

    rol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Madagascar
    -0.06
    _client
    -0.06
    eten
    -0.06
     Stack
    -0.06
    )//
    -0.06
    ++;↵
    -0.06
    Idle
    -0.05
    Consumer
    -0.05
    .asarray
    -0.05
     uží
    -0.05
    POSITIVE LOGITS
     pains
    0.07
     reassuring
    0.07
    ени
    0.07
    velopment
    0.07
     scars
    0.06
     histograms
    0.06
     Carla
    0.06
    marshall
    0.06
    imientos
    0.06
    時
    0.06
    Act Density 0.003%

    No Known Activations