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

    Neuronpedia

    INDEX
    Explanations

    another other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )t
    -0.07
     eens
    -0.06
    ]*)
    -0.06
    _sensor
    -0.06
    capt
    -0.06
    ated
    -0.06
     disco
    -0.06
     "")
↵
    -0.06
    速
    -0.06
     ubyt
    -0.06
    POSITIVE LOGITS
     REMOVE
    0.07
     MPG
    0.07
    utches
    0.07
     Other
    0.06
    �
    0.06
     Blogger
    0.06
    �
    0.06
     hears
    0.06
    ��
    0.06
     kop
    0.06
    Act Density 0.039%

    No Known Activations