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

    Neuronpedia

    INDEX
    Explanations

    Artificial intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Darth
    -0.07
     distressed
    -0.07
    Senate
    -0.07
    quiv
    -0.06
    ier
    -0.06
     ownerId
    -0.06
    Soap
    -0.06
     cement
    -0.06
    (skip
    -0.06
     plywood
    -0.06
    POSITIVE LOGITS
    _UNIFORM
    0.07
     haciendo
    0.07
    _UINT
    0.07
     perpetrated
    0.07
     sự
    0.06
     بص
    0.06
     ان
    0.06
     pasado
    0.06
     Prozent
    0.06
     відвід
    0.06
    Act Density 0.022%

    No Known Activations