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
     لماذا
    -0.07
    旁
    -0.07
    rometer
    -0.07
    %),
    -0.07
    😨
    -0.07
    女性朋友
    -0.07
     resurrect
    -0.07
     Warfare
    -0.06
     documenting
    -0.06
    ellungen
    -0.06
    POSITIVE LOGITS
    EMU
    0.07
    clas
    0.07
    Finite
    0.07
    ient
    0.07
    angep
    0.06
    unei
    0.06
    .MenuItem
    0.06
    valu
    0.06
    _birth
    0.06
    .blit
    0.06
    Act Density 0.047%

    No Known Activations