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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consejos
    -0.08
     advies
    -0.08
     aconse
    -0.08
     collo
    -0.08
     Alem
    -0.08
    -Mail
    -0.08
    ,new
    -0.08
     shocked
    -0.08
     caretaker
    -0.07
     saddle
    -0.07
    POSITIVE LOGITS
     compliance
    0.12
    Compliance
    0.12
    符合
    0.12
    对应
    0.11
     Compliance
    0.11
     conformité
    0.11
    Coverage
    0.11
     cumplimiento
    0.10
     complies
    0.10
     Coverage
    0.10
    Act Density 0.062%

    No Known Activations