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

    Neuronpedia

    INDEX
    Explanations

    words related to importance and usefulness combined with prepositions

    oai_token-act-pair · gemini-2.0-flash

    Importance and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.73
     nahilalakip
    -0.73
     defaultstate
    -0.73
     שוליים
    -0.71
    }],
    -0.69
     GenerationType
    -0.68
     EconPapers
    -0.67
    }]
    -0.66
     Мексичка
    -0.66
    principalTable
    -0.65
    POSITIVE LOGITS
    mbggenerated
    0.43
    T
    0.43
    common
    0.42
     Ker
    0.40
     ker
    0.39
    珊
    0.39
    weaver
    0.38
     devenue
    0.38
     rock
    0.38
    et
    0.38
    Act Density 2.393%

    No Known Activations