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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shortly
    -0.07
    Shortly
    -0.07
     ich
    -0.06
    ocado
    -0.06
    ificado
    -0.06
    boru
    -0.06
     mús
    -0.06
     sequences
    -0.06
    tickets
    -0.06
     actividades
    -0.06
    POSITIVE LOGITS
    (KERN
    0.07
     PAC
    0.07
     レディース
    0.07
     élect
    0.06
    PARAM
    0.06
    _rom
    0.06
     bullpen
    0.06
     valuable
    0.06
    ;-
    0.06
     facilitating
    0.06
    Act Density 0.042%

    No Known Activations