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

    Neuronpedia

    INDEX
    Explanations

    alpha and gamma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    💦
    -0.09
     nationwide
    -0.08
    🐅
    -0.08
    مد
    -0.08
    袁
    -0.07
    Fa
    -0.07
     vont
    -0.07
     acknowledge
    -0.07
     vra
    -0.07
     saldırı
    -0.07
    POSITIVE LOGITS
    (interface
    0.08
    .deck
    0.08
    anguages
    0.07
     roast
    0.07
    emodel
    0.07
    ATTERN
    0.07
    	label
    0.07
    	index
    0.07
    _Interface
    0.07
     terminated
    0.07
    Act Density 0.004%

    No Known Activations