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
     binh
    -0.07
    중에
    -0.07
     Vanilla
    -0.07
     fanc
    -0.06
     Canc
    -0.06
     Pediatric
    -0.06
     �
    -0.06
    çi
    -0.06
     settled
    -0.06
    zM
    -0.06
    POSITIVE LOGITS
     вияв
    0.06
    imenti
    0.06
    Datos
    0.06
    cake
    0.06
    utting
    0.06
    iska
    0.06
    artisanlib
    0.06
    switch
    0.06
    _sell
    0.06
     instruction
    0.06
    Act Density 0.090%

    No Known Activations