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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vars
    -0.07
    Venta
    -0.06
    "):
    -0.06
    coil
    -0.06
    	play
    -0.06
     sergeant
    -0.06
    heroes
    -0.06
    worked
    -0.06
     Bust
    -0.06
     perfil
    -0.06
    POSITIVE LOGITS
     medically
    0.06
     федераль
    0.06
     hotelu
    0.06
     mnemonic
    0.06
    VERTISE
    0.06
    .clip
    0.06
     쪽
    0.06
    なんて
    0.06
     Wikipedia
    0.06
     Computer
    0.06
    Act Density 0.031%

    No Known Activations