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

    Neuronpedia

    INDEX
    Explanations

    Docker images, documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fixation
    -0.08
     consume
    -0.07
     Unternehmen
    -0.07
    身子
    -0.07
    ﮎ
    -0.07
     fibonacci
    -0.07
    setParameter
    -0.06
    出生于
    -0.06
     После
    -0.06
    iju
    -0.06
    POSITIVE LOGITS
     preferences
    0.08
    ------+------+
    0.08
     Neighbor
    0.08
     (_
    0.07
     IF
    0.06
    ░
    0.06
    }}</
    0.06
     pneum
    0.06
     UIAlert
    0.06
    ("</
    0.06
    Act Density 0.000%

    No Known Activations