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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SmartyHeaderCode
    -0.06
    antee
    -0.06
    parm
    -0.06
    genesis
    -0.06
    alls
    -0.06
    irut
    -0.06
    _areas
    -0.06
    ises
    -0.06
    bursement
    -0.06
    lando
    -0.06
    POSITIVE LOGITS
    （
    0.08
     Она
    0.07
     were
    0.07
     differed
    0.07
     could
    0.07
    '},
↵
    0.07
    并不
    0.07
     �
    0.07
     되었다
    0.06
    			
↵
    0.06
    Act Density 0.098%

    No Known Activations