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

    Neuronpedia

    INDEX
    Explanations

    Abstract

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Group
    -0.08
    elor
    -0.06
    スク
    -0.06
     дисцип
    -0.06
     місці
    -0.06
    .lines
    -0.06
     hierarchy
    -0.06
     liability
    -0.06
    antor
    -0.06
    атель
    -0.06
    POSITIVE LOGITS
    ((&___
    0.07
     골
    0.06
     Knee
    0.06
    �
    0.06
     painstaking
    0.06
     elk
    0.06
     Hunters
    0.06
    aines
    0.06
     дор
    0.06
     ум
    0.06
    Act Density 0.003%

    No Known Activations