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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Service
    -0.08
     concatenated
    -0.07
     clientes
    -0.06
     ISO
    -0.06
     Hermes
    -0.06
     EX
    -0.06
    .sales
    -0.06
     domina
    -0.06
    _servers
    -0.06
    거리
    -0.06
    POSITIVE LOGITS
     регуляр
    0.07
    films
    0.06
    olik
    0.06
    поч
    0.06
    -g
    0.06
    []↵
    0.06
    .unpack
    0.06
     :.:
    0.06
    ailing
    0.06
    FORMANCE
    0.06
    Act Density 0.009%

    No Known Activations