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

    Neuronpedia

    INDEX
    Explanations

    choose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ゾ
    -0.08
    effect
    -0.07
    WORD
    -0.07
     seek
    -0.07
     evaluating
    -0.06
     equations
    -0.06
    apro
    -0.06
     cycles
    -0.06
    	width
    -0.06
     calam
    -0.06
    POSITIVE LOGITS
     suede
    0.07
     jedn
    0.06
    候
    0.06
    -select
    0.06
    Theta
    0.06
    γγελ
    0.06
    .policy
    0.06
    ,color
    0.06
     elephant
    0.06
     contenu
    0.06
    Act Density 0.012%

    No Known Activations