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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    足球
    -0.07
     puff
    -0.07
     antic
    -0.07
    .Status
    -0.07
     Si
    -0.07
     requis
    -0.07
    Growing
    -0.07
    ++)↵
    -0.07
     floral
    -0.06
     surviv
    -0.06
    POSITIVE LOGITS
    (gulp
    0.07
    TARGET
    0.06
    _rsp
    0.06
    esign
    0.06
    итися
    0.06
    _solve
    0.06
     اع
    0.06
    _sep
    0.06
    _play
    0.06
    rám
    0.06
    Act Density 0.008%

    No Known Activations