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
     شرح
    -0.07
    .await
    -0.06
    Canonical
    -0.06
    challenge
    -0.06
    .Aggressive
    -0.06
     Ник
    -0.06
    	sw
    -0.06
    ührung
    -0.06
     exercising
    -0.06
     darken
    -0.06
    POSITIVE LOGITS
     Sapphire
    0.07
    (meta
    0.07
    ightly
    0.07
    mont
    0.06
     bụi
    0.06
     POST
    0.06
     ministry
    0.06
    _was
    0.06
    .Thread
    0.06
    apphire
    0.06
    Act Density 0.020%

    No Known Activations