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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     semaphore
    -0.07
     フ
    -0.07
     "\""
    -0.06
    Usage
    -0.06
    ("\"
    -0.06
    _invite
    -0.06
    ーパ
    -0.06
     bent
    -0.06
     columnist
    -0.06
     generics
    -0.06
    POSITIVE LOGITS
     Gard
    0.07
    ipsis
    0.07
    _collections
    0.06
    Tpl
    0.06
    SceneManager
    0.06
    paren
    0.06
     suppress
    0.06
     Boh
    0.06
    πί
    0.06
     bach
    0.06
    Act Density 0.064%

    No Known Activations