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
    αλύτε
    -0.07
    ingles
    -0.07
    �
    -0.06
     підс
    -0.06
    rze
    -0.06
    Blockly
    -0.06
     Seems
    -0.06
    _representation
    -0.06
    oct
    -0.06
    ระบบ
    -0.06
    POSITIVE LOGITS
    _grp
    0.06
    [arg
    0.06
     thanking
    0.06
    firebase
    0.06
    empre
    0.06
    072
    0.06
    .samples
    0.06
    	x
    0.06
    410
    0.06
     Alleg
    0.05
    Act Density 0.000%

    No Known Activations