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

    Neuronpedia

    INDEX
    Explanations

    directory traversal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lices
    -0.07
     ↵  ↵
    -0.07
     curiosity
    -0.07
    __.
    -0.07
    ��
    -0.07
    NESS
    -0.07
    ät
    -0.07
    ⽰
    -0.06
    �
    -0.06
    @(
    -0.06
    POSITIVE LOGITS
     proficient
    0.07
     impressions
    0.07
    ipline
    0.07
     unge
    0.06
    pressions
    0.06
    呖
    0.06
    _REMOVE
    0.06
    未來
    0.06
     factory
    0.06
    UpDown
    0.06
    Act Density 0.000%

    No Known Activations