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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Talent
    -0.07
    -U
    -0.07
    responsive
    -0.07
    	G
    -0.06
    hum
    -0.06
    Navigation
    -0.06
    props
    -0.06
     پوش
    -0.06
    -g
    -0.06
    Bon
    -0.06
    POSITIVE LOGITS
    _refptr
    0.07
    entrada
    0.06
     �
    0.06
    ामल
    0.06
    兄
    0.06
    扫
    0.06
    (arr
    0.06
     reconcile
    0.06
     HRESULT
    0.06
     sorted
    0.06
    Act Density 0.098%

    No Known Activations