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

    Neuronpedia

    INDEX
    Explanations

    clarify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seab
    -0.07
     Potential
    -0.07
     poo
    -0.07
    osos
    -0.06
    indow
    -0.06
     outputStream
    -0.06
     heap
    -0.06
    Projectile
    -0.06
    omb
    -0.06
    696
    -0.06
    POSITIVE LOGITS
     clarification
    0.09
     clarified
    0.09
    klär
    0.09
     Clarke
    0.08
    clare
    0.08
     clarify
    0.08
     уточ
    0.08
    átor
    0.08
    烦
    0.07
     clar
    0.07
    Act Density 0.010%

    No Known Activations