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

    Neuronpedia

    INDEX
    Explanations

    detects anger

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (member
    -0.07
     ber
    -0.07
    135
    -0.06
     tray
    -0.06
    بان
    -0.06
    35
    -0.06
    Queue
    -0.06
     chorus
    -0.06
     IX
    -0.06
    28
    -0.06
    POSITIVE LOGITS
    νης
    0.06
     escorts
    0.06
    ALT
    0.06
     ẩn
    0.06
    ;;;;;;;;;;;;;;;;
    0.06
    building
    0.06
     ";
    0.06
    	DWORD
    0.06
     staples
    0.06
     sürdür
    0.06
    Act Density 0.263%

    No Known Activations