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

    Neuronpedia

    INDEX
    Explanations

    Artgerm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Robin
    0.45
    ဿ
    0.44
     Robin
    0.42
     Robbins
    0.41
    𝐾
    0.40
     robin
    0.39
    residuals
    0.37
    eres
    0.34
    krb
    0.34
    darwin
    0.34
    POSITIVE LOGITS
    巴
    0.42
     Barbosa
    0.36
    蕗
    0.35
     Figue
    0.34
     Ba
    0.34
     巴
    0.34
    Agu
    0.33
     Bae
    0.33
     Bue
    0.33
     감
    0.33
    Act Density 0.002%

    No Known Activations