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

    Neuronpedia

    INDEX
    Explanations

    ham

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pollution
    -0.09
     Stainless
    -0.08
     Advertising
    -0.08
     pared
    -0.08
     clutter
    -0.08
     stamping
    -0.08
     freg
    -0.08
     ceg
    -0.08
     तस्वीर
    -0.07
     Crisp
    -0.07
    POSITIVE LOGITS
     muscles
    0.09
     proteins
    0.09
     músculos
    0.08
    idepress
    0.08
     idosos
    0.08
    iores
    0.08
     muscle
    0.08
     instincts
    0.08
     valleys
    0.07
     reservas
    0.07
    Act Density 0.004%

    No Known Activations