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

    Neuronpedia

    INDEX
    Explanations

    Themes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UDENT
    -0.07
    Juan
    -0.06
     employs
    -0.06
    .JSON
    -0.06
    譜
    -0.06
    _RESPONSE
    -0.06
    _CATEGORY
    -0.06
    Europe
    -0.06
    клад
    -0.06
     Francisco
    -0.06
    POSITIVE LOGITS
     mimo
    0.07
    reachable
    0.07
    cılık
    0.07
     plead
    0.07
     @$_
    0.07
    @protocol
    0.06
    (delete
    0.06
    .month
    0.06
     случ
    0.06
    .isNotBlank
    0.06
    Act Density 0.106%

    No Known Activations