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

    Neuronpedia

    INDEX
    Explanations

    driving away

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    crm
    -0.07
    downloads
    -0.07
    DIRECTORY
    -0.06
     Emails
    -0.06
     wrong
    -0.06
     massively
    -0.06
     reef
    -0.06
     translations
    -0.06
    濃
    -0.06
     leopard
    -0.06
    POSITIVE LOGITS
     Şirket
    0.07
    _fn
    0.06
     casa
    0.06
    regist
    0.06
    _gt
    0.06
     паль
    0.06
     TOTAL
    0.06
     státy
    0.06
     demonstr
    0.06
     počet
    0.06
    Act Density 0.021%

    No Known Activations