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

    Neuronpedia

    INDEX
    Explanations

    books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ctrl
    -0.08
    (foo
    -0.07
    ू
    -0.06
    ("|
    -0.06
     ridiculous
    -0.06
     borr
    -0.06
    institution
    -0.06
     sổ
    -0.06
    \uC
    -0.06
    ミュ
    -0.06
    POSITIVE LOGITS
    estatus
    0.07
     dwell
    0.06
     stacks
    0.06
     Landing
    0.06
     objectMapper
    0.06
     meets
    0.06
     unemployed
    0.06
     chairman
    0.06
    ="/
    0.06
    的心
    0.06
    Act Density 0.144%

    No Known Activations