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

    Neuronpedia

    INDEX
    Explanations

    bless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ccd
    -0.07
     Nh
    -0.07
    黨
    -0.07
     berlin
    -0.07
     indu
    -0.06
    õ
    -0.06
     выпол
    -0.06
    擔
    -0.06
    nr
    -0.06
     Representative
    -0.06
    POSITIVE LOGITS
    abstractmethod
    0.08
     terminology
    0.08
     smells
    0.08
     Marxism
    0.07
    orks
    0.07
    :\"
    0.07
    _ISR
    0.07
     puzzles
    0.07
     shells
    0.07
     prized
    0.07
    Act Density 0.014%

    No Known Activations