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

    Neuronpedia

    INDEX
    Explanations

    (name

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لديك
    -0.08
     Radar
    -0.07
    蘑菇
    -0.07
    Evaluation
    -0.07
    _output
    -0.07
    他自己
    -0.07
     silicon
    -0.07
     nuclear
    -0.07
    幕后
    -0.07
     utilisateur
    -0.07
    POSITIVE LOGITS
    >>;↵
    0.07
     Респ
    0.07
    剟
    0.07
     [{'
    0.07
    .gridx
    0.06
     Müdürlüğü
    0.06
    >$
    0.06
    	mp
    0.06
     Worce
    0.06
    洨
    0.06
    Act Density 0.001%

    No Known Activations