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

    Neuronpedia

    INDEX
    Explanations

    backslash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anch
    -0.08
    iculos
    -0.08
     Anyone
    -0.08
    apters
    -0.08
    (tool
    -0.08
    obsolete
    -0.07
    _ctl
    -0.07
    ｺ
    -0.07
     Öl
    -0.07
    .Channel
    -0.07
    POSITIVE LOGITS
    restrict
    0.07
    .EMAIL
    0.07
    הבנה
    0.07
    家务
    0.07
    并将
    0.06
    社会保障
    0.06
    两
    0.06
    แยก
    0.06
     blessings
    0.06
    �
    0.06
    Act Density 0.026%

    No Known Activations