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

    Neuronpedia

    INDEX
    Explanations

    actors and acting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     produced
    -0.07
    .met
    -0.06
     Acres
    -0.06
    Fish
    -0.06
    _REG
    -0.06
     arrayList
    -0.06
    entions
    -0.06
    Removed
    -0.06
    acher
    -0.06
    995
    -0.06
    POSITIVE LOGITS
     půl
    0.07
    neum
    0.06
     поє
    0.06
    Fuck
    0.06
     IOC
    0.06
     inh
    0.06
     geral
    0.06
    usual
    0.06
     noe
    0.06
     Gover
    0.06
    Act Density 0.022%

    No Known Activations