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

    Neuronpedia

    INDEX
    Explanations

    fear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Expected
    -0.08
    Uni
    -0.08
     attendu
    -0.08
     esperado
    -0.08
     autorizado
    -0.08
     produzido
    -0.08
     رات
    -0.08
     vecinos
    -0.08
     housekeeping
    -0.08
     contempor
    -0.07
    POSITIVE LOGITS
     crip
    0.10
     sufferers
    0.10
     debilitating
    0.10
     Speech
    0.09
     catastroph
    0.09
    prechen
    0.09
     ingr
    0.09
    阻
    0.08
     simptom
    0.08
    �
    0.08
    Act Density 0.025%

    No Known Activations