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

    Neuronpedia

    INDEX
    Explanations

    visualizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dere
    -0.07
    warm
    -0.07
     حو
    -0.07
    atrix
    -0.06
    irm
    -0.06
     Natal
    -0.06
     nostr
    -0.06
    terior
    -0.06
    _formula
    -0.06
    otre
    -0.06
    POSITIVE LOGITS
     HS
    0.06
     preferred
    0.06
     Extensions
    0.06
    _OWNER
    0.06
    EEP
    0.06
     characteristic
    0.06
     М
    0.06
     amounts
    0.05
    .im
    0.05
    .select
    0.05
    Act Density 0.054%

    No Known Activations