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

    Neuronpedia

    INDEX
    Explanations

    friendship and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hermano
    -0.09
     naughty
    -0.08
    .Expression
    -0.08
     correto
    -0.08
     Speedway
    -0.08
    .expression
    -0.08
     Year's
    -0.08
     promedio
    -0.08
     Einkommen
    -0.08
     Hans
    -0.08
    POSITIVE LOGITS
    芽
    0.08
    ometer
    0.08
     tann
    0.08
    dent
    0.08
    sup
    0.08
    woven
    0.07
    ega
    0.07
    lens
    0.07
    rings
    0.07
    zers
    0.07
    Act Density 0.016%

    No Known Activations