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

    Neuronpedia

    INDEX
    Explanations

    skewers and toothpicks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     presumably
    -0.06
     resultSet
    -0.06
    dataset
    -0.06
     trusting
    -0.06
     Syndrome
    -0.06
    ians
    -0.06
     Highlight
    -0.06
     Crist
    -0.06
    Password
    -0.06
    _PHASE
    -0.06
    POSITIVE LOGITS
     sexuales
    0.06
     تخصص
    0.06
     уд
    0.06
    Unity
    0.06
     dayan
    0.06
     postfix
    0.06
    _contin
    0.06
    mamak
    0.06
     milfs
    0.06
     independ
    0.06
    Act Density 0.024%

    No Known Activations