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

    Neuronpedia

    INDEX
    Explanations

    German text with verbs and adjectives

    oai_token-act-pair · gemini-2.0-flash

    german

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ting
    -0.63
     Weller
    -0.53
     отно
    -0.53
    inos
    -0.52
    гово
    -0.52
     comer
    -0.52
     hit
    -0.51
     الدولى
    -0.50
    amerikanischer
    -0.49
     body
    -0.48
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.92
    ⓧ
    0.82
    InvalidProtocol
    0.77
    帖最后由
    0.73
     propOrder
    0.73
    Autoritní
    0.73
    Personendaten
    0.73
    esModule
    0.72
    ůli
    0.72
    InstanceState
    0.68
    Act Density 0.362%

    No Known Activations