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

    Neuronpedia

    INDEX
    Explanations

    objection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _triggered
    -0.07
    �
    -0.07
    cplusplus
    -0.07
    .un
    -0.06
    .begin
    -0.06
     zwe
    -0.06
     αρι
    -0.06
    .didReceiveMemoryWarning
    -0.06
    (pDX
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     objections
    0.10
     objection
    0.08
    /ss
    0.07
    notated
    0.07
    ug
    0.07
     irritating
    0.07
     objected
    0.07
    ط
    0.07
    ाइक
    0.07
     Radical
    0.07
    Act Density 0.003%

    No Known Activations