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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ்�
    -0.07
    Joy
    -0.07
     intimid
    -0.06
     SES
    -0.06
    евер
    -0.06
     discriminatory
    -0.06
    _Level
    -0.06
    ']+
    -0.06
    laden
    -0.06
     Decimal
    -0.06
    POSITIVE LOGITS
     discern
    0.07
     Views
    0.07
    /password
    0.07
    -basket
    0.07
    .Signal
    0.06
     gdk
    0.06
    article
    0.06
     rocks
    0.06
     strangely
    0.06
     Produced
    0.06
    Act Density 0.013%

    No Known Activations