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

    Neuronpedia

    INDEX
    Explanations

    amplified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	scene
    -0.08
    203
    -0.07
    겠
    -0.07
    死
    -0.07
     desc
    -0.07
    _DEFINED
    -0.07
     Sexe
    -0.07
     Kosovo
    -0.07
     Naz
    -0.07
     marché
    -0.07
    POSITIVE LOGITS
     Ampl
    0.10
     amplify
    0.07
     amplified
    0.07
     ampl
    0.07
    _;↵
    0.07
     Alf
    0.07
    reactstrap
    0.07
    isper
    0.06
     تلفن
    0.06
    Slim
    0.06
    Act Density 0.010%

    No Known Activations