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

    Neuronpedia

    INDEX
    Explanations

    interested

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    move
    -0.08
    _PUSH
    -0.07
     glory
    -0.06
    roids
    -0.06
    _texts
    -0.06
    Trait
    -0.06
    ς
    -0.06
     Williamson
    -0.06
    Credential
    -0.06
     rape
    -0.06
    POSITIVE LOGITS
    ρει
    0.08
     dresses
    0.07
     sorun
    0.07
     interested
    0.06
    spir
    0.06
     unders
    0.06
     regist
    0.06
    Ÿ
    0.06
    /script
    0.06
    .setScene
    0.06
    Act Density 0.012%

    No Known Activations