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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RH
    -0.07
     
    -0.07
     perch
    -0.06
     �
    -0.06
     Pens
    -0.06
    ・マ
    -0.06
     The
    -0.06
     (
    -0.06
     Hos
    -0.06
     qu
    -0.06
    POSITIVE LOGITS
     янва
    0.07
    adır
    0.07
    >↵↵↵↵↵
    0.07
    .↵↵↵↵
    0.07
    	damage
    0.07
    илася
    0.07
     })↵↵
    0.07
    ;)
    0.07
    /)
    0.07
    ありがとう
    0.07
    Act Density 0.062%

    No Known Activations