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

    Neuronpedia

    INDEX
    Explanations

    to/against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -moving
    -0.08
    ्रव
    -0.07
    )||
    -0.07
    /|
    -0.07
    악
    -0.06
     powers
    -0.06
     grav
    -0.06
     peer
    -0.06
     invest
    -0.06
     probation
    -0.06
    POSITIVE LOGITS
    anium
    0.07
     з
    0.07
    ?↵
    0.06
     sincerely
    0.06
    ichick
    0.06
     Soldier
    0.06
     โรง
    0.06
    …↵
    0.06
     شمالی
    0.06
     Css
    0.06
    Act Density 0.029%

    No Known Activations