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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .onSubmit
    -0.08
     sessionId
    -0.08
     getSession
    -0.07
     conformity
    -0.07
     manifesto
    -0.07
     kiên
    -0.07
    좃
    -0.07
    ovenant
    -0.07
     pau
    -0.07
    _SENS
    -0.07
    POSITIVE LOGITS
     strings
    0.07
     Therapy
    0.07
    [-
    0.07
    力量
    0.07
     crops
    0.07
    /(?
    0.06
     charging
    0.06
    不僅
    0.06
     dagen
    0.06
    "+"
    0.06
    Act Density 0.057%

    No Known Activations