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

    Neuronpedia

    INDEX
    Explanations

    mechanical controls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inceton
    -0.08
     Recover
    -0.07
    不行
    -0.07
     effectively
    -0.07
    十足
    -0.07
     uy
    -0.07
     бук
    -0.07
    ük
    -0.07
    带给
    -0.06
     positivity
    -0.06
    POSITIVE LOGITS
     Girls
    0.07
    .Internal
    0.07
    /static
    0.07
     admin
    0.07
    👉
    0.07
     dựng
    0.07
    -sidebar
    0.06
    clerosis
    0.06
    _Device
    0.06
    싣
    0.06
    Act Density 0.041%

    No Known Activations