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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unlike
    -0.06
     XOR
    -0.06
     Rotation
    -0.06
     dispute
    -0.06
     deals
    -0.06
     pedal
    -0.06
    ============↵
    -0.06
    _music
    -0.06
     Education
    -0.06
    нож
    -0.06
    POSITIVE LOGITS
     الس
    0.07
    anything
    0.07
    .getC
    0.06
    successfully
    0.06
    十四
    0.06
     их
    0.06
     GIVEN
    0.06
    สามารถ
    0.06
     усе
    0.06
     forgiveness
    0.06
    Act Density 0.075%

    No Known Activations