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

    Neuronpedia

    INDEX
    Explanations

    positive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цвет
    -0.07
    darwin
    -0.07
    itant
    -0.07
    getPost
    -0.07
    CHEDULE
    -0.07
    URRENT
    -0.07
    "At
    -0.07
    door
    -0.07
    pace
    -0.07
    いう
    -0.06
    POSITIVE LOGITS
     nic
    0.06
    xDB
    0.06
     خارجية
    0.06
     hap
    0.05
     büny
    0.05
    _cou
    0.05
    Imm
    0.05
     geen
    0.05
     ホ
    0.05
    ラン
    0.05
    Act Density 0.000%

    No Known Activations