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

    Neuronpedia

    INDEX
    Explanations

    "no"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highly
    -0.07
    Flying
    -0.07
     formed
    -0.06
    +d
    -0.06
     Leban
    -0.06
     PH
    -0.06
     Adaptive
    -0.06
    (depend
    -0.06
     biography
    -0.06
     always
    -0.06
    POSITIVE LOGITS
    たちは
    0.07
     대행
    0.07
    기는
    0.06
    >/
    0.06
    …I
    0.06
    bear
    0.06
     �
    0.06
     unrealistic
    0.06
    …the
    0.06
     eof
    0.06
    Act Density 0.020%

    No Known Activations