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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хлоп
    -0.08
    _FF
    -0.07
    _CONV
    -0.06
    �
    -0.06
    _Message
    -0.06
    StandardItem
    -0.06
    _METHOD
    -0.06
    USES
    -0.06
    _sv
    -0.06
    TOP
    -0.06
    POSITIVE LOGITS
     béné
    0.07
     según
    0.07
    	j
    0.07
    inged
    0.07
     В
    0.06
     vendors
    0.06
     statewide
    0.06
     halinde
    0.06
     strong
    0.06
     xã
    0.06
    Act Density 0.025%

    No Known Activations