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

    Neuronpedia

    INDEX
    Explanations

    ow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .BAD
    -0.07
    	store
    -0.07
    294
    -0.06
    )")↵↵
    -0.06
    Spain
    -0.06
     pooling
    -0.06
     Second
    -0.06
    (cos
    -0.06
     blocked
    -0.06
    ЛО
    -0.06
    POSITIVE LOGITS
    енная
    0.07
    _wf
    0.07
    :min
    0.06
    .gson
    0.06
     formulario
    0.06
    (newState
    0.06
     Params
    0.06
    azione
    0.06
     picnic
    0.06
    (Blueprint
    0.06
    Act Density 0.020%

    No Known Activations