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

    Neuronpedia

    INDEX
    Explanations

    working well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vention
    -0.06
    _python
    -0.06
    .height
    -0.06
    CMS
    -0.06
    ुस
    -0.06
     Merr
    -0.06
    aker
    -0.06
    Rows
    -0.06
    уття
    -0.06
    jective
    -0.06
    POSITIVE LOGITS
    ">×</
    0.08
     watershed
    0.07
     Wrath
    0.07
    енным
    0.07
     Най
    0.07
    confirmed
    0.06
     Vampire
    0.06
     explosions
    0.06
    ICH
    0.06
    äre
    0.06
    Act Density 0.013%

    No Known Activations