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

    Neuronpedia

    INDEX
    Explanations

    influential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nord
    -0.07
    ┘
    -0.06
    ross
    -0.06
     objet
    -0.06
     Customer
    -0.06
    肯
    -0.06
    -placement
    -0.06
    �
    -0.06
    promise
    -0.06
    čit
    -0.06
    POSITIVE LOGITS
     influential
    0.18
     Dev
    0.07
     impactful
    0.07
     critical
    0.06
     winding
    0.06
    _coeff
    0.06
    .spec
    0.06
     had
    0.06
    	start
    0.06
     phần
    0.06
    Act Density 0.006%

    No Known Activations