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

    Neuronpedia

    INDEX
    Explanations

    Apache software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gates
    -0.07
     Pointer
    -0.07
    Iterable
    -0.06
    adow
    -0.06
    AYER
    -0.06
     Anth
    -0.06
     takový
    -0.06
     Hey
    -0.06
    chal
    -0.06
    uzzer
    -0.06
    POSITIVE LOGITS
     Published
    0.07
    시는
    0.06
    Configurer
    0.06
    .Pr
    0.06
    0.06
    0.06
     Val
    0.06
     ebp
    0.06
     Champ
    0.06
               
    0.06
    Act Density 0.005%

    No Known Activations