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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jedné
    -0.07
    整
    -0.07
    (or
    -0.07
    _YES
    -0.06
    �
    -0.06
     pcs
    -0.06
     stepping
    -0.06
    avigate
    -0.06
     principalTable
    -0.06
     callers
    -0.06
    POSITIVE LOGITS
    prime
    0.06
     Mercer
    0.06
     mình
    0.06
     Miami
    0.06
     menacing
    0.06
    avatel
    0.06
    iloc
    0.06
    empt
    0.06
    	move
    0.06
     fuer
    0.05
    Act Density 0.126%

    No Known Activations