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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    765
    -0.07
     Iter
    -0.07
    Emma
    -0.07
    adratic
    -0.07
     Wol
    -0.06
    .theta
    -0.06
    _ant
    -0.06
    攻撃
    -0.06
    ケース
    -0.06
    obby
    -0.06
    POSITIVE LOGITS
     about
    0.08
     affiliation
    0.07
     proclamation
    0.07
     Thailand
    0.07
     PCB
    0.07
     patrols
    0.06
     trừ
    0.06
     approximately
    0.06
    capability
    0.06
    -fashioned
    0.06
    Act Density 0.004%

    No Known Activations