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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (write
    -0.08
    ograms
    -0.08
    irable
    -0.08
    &oacute
    -0.08
    uable
    -0.08
     tương
    -0.08
    -0.07
     safeguard
    -0.07
    iero
    -0.07
     супрацоў
    -0.07
    POSITIVE LOGITS
     Tener
    0.09
    relationship
    0.08
     nostalg
    0.08
    会上
    0.08
     heav
    0.07
    ਟਰ
    0.07
     accrued
    0.07
     Erinnerung
    0.07
     ਸਭ
    0.07
     देखकर
    0.07
    Act Density 0.005%
    No Known Activations