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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NotEmpty
    -0.07
     Seminar
    -0.07
    需求
    -0.06
    ']])↵
    -0.06
    NP
    -0.06
    ович
    -0.06
    amiliar
    -0.06
     números
    -0.06
     Richardson
    -0.06
    很多
    -0.06
    POSITIVE LOGITS
    orts
    0.06
     dg
    0.06
     dak
    0.06
    猫
    0.06
    (dx
    0.06
     boot
    0.06
     Bills
    0.06
    _BGR
    0.06
     componentWill
    0.06
     delicate
    0.06
    Act Density 0.001%

    No Known Activations