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

    Neuronpedia

    INDEX
    Explanations

    overfitting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    criteria
    -0.08
    ์ด
    -0.07
    eko
    -0.07
    elect
    -0.07
    iph
    -0.07
    -=
    -0.06
    -sided
    -0.06
    เกม
    -0.06
    (Service
    -0.06
    ät
    -0.06
    POSITIVE LOGITS
     subtype
    0.22
    subtype
    0.10
    _subtype
    0.08
     ^{↵
    0.07
     Smoking
    0.07
     Writing
    0.06
     Vikings
    0.06
     Santos
    0.06
    cape
    0.06
     Sound
    0.06
    Act Density 0.003%

    No Known Activations