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

    Neuronpedia

    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /New
    -0.07
     넣
    -0.07
    _bad
    -0.06
    〔
    -0.06
    SEP
    -0.06
    /front
    -0.06
     poměr
    -0.06
    linkedin
    -0.06
     velký
    -0.06
    ену
    -0.06
    POSITIVE LOGITS
    atives
    0.06
     vocabulary
    0.06
     Moderator
    0.06
     Bonnie
    0.06
     Column
    0.06
     Globals
    0.06
     PAGE
    0.06
     flawed
    0.06
     Prison
    0.06
    .simps
    0.06
    Act Density 0.000%

    No Known Activations