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

    Neuronpedia

    INDEX
    Explanations

    Code/script snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zed
    -0.07
    ورش
    -0.06
    “The
    -0.06
    �
    -0.06
     Focus
    -0.06
    zk
    -0.06
    set
    -0.06
    	ADD
    -0.06
    other
    -0.06
    rowing
    -0.06
    POSITIVE LOGITS
     Ramp
    0.07
     sur
    0.07
    Draft
    0.07
    バス
    0.07
     keer
    0.06
     représ
    0.06
    ้าหน
    0.06
     studs
    0.06
    _ARGUMENT
    0.06
    "',
    0.06
    Act Density 0.030%

    No Known Activations