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

    Neuronpedia

    INDEX
    Explanations

    Code/software libraries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suiv
    -0.07
    vised
    -0.07
     Assassin
    -0.06
    .sql
    -0.06
    ered
    -0.06
    ս
    -0.06
     xây
    -0.06
     wygl
    -0.06
    楦
    -0.06
    -F
    -0.06
    POSITIVE LOGITS
     stri
    0.07
    Р
    0.07
    港
    0.07
     Hampton
    0.07
     bumps
    0.07
    原因是
    0.06
    intel
    0.06
     Pull
    0.06
    vironment
    0.06
    To
    0.06
    Act Density 0.000%

    No Known Activations