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

    Neuronpedia

    INDEX
    Explanations

    or and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REMOVE
    -0.07
     pob
    -0.07
     Ming
    -0.06
    utowired
    -0.06
     ott
    -0.06
    〃
    -0.06
     trad
    -0.06
    Ban
    -0.06
    (text
    -0.06
    .ll
    -0.06
    POSITIVE LOGITS
    て
    0.07
    izzer
    0.06
    structuring
    0.06
     disappointment
    0.06
    -face
    0.06
     appointment
    0.06
     मर
    0.06
     اشاره
    0.06
     Cannon
    0.06
     inactive
    0.06
    Act Density 0.026%

    No Known Activations