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

    Neuronpedia

    INDEX
    Explanations

    membranes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISING
    -0.08
    руз
    -0.07
     });
    -0.07
     Negro
    -0.07
     عملی
    -0.07
    úb
    -0.07
    Json
    -0.07
    efully
    -0.07
     EVEN
    -0.07
     buckets
    -0.07
    POSITIVE LOGITS
     serge
    0.07
    (loader
    0.06
     ي
    0.06
    都
    0.06
    ρκε
    0.06
    رك
    0.06
     đa
    0.06
    익
    0.06
    809
    0.05
    (describing
    0.05
    Act Density 0.039%

    No Known Activations