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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    belt
    -0.07
    隊
    -0.06
    别
    -0.06
    また
    -0.06
    _SWITCH
    -0.06
     Girl
    -0.06
     ngũ
    -0.06
     Boss
    -0.06
     avoid
    -0.06
     Northwest
    -0.06
    POSITIVE LOGITS
    Follow
    0.07
    specifier
    0.06
     impact
    0.06
    ocrisy
    0.06
    ereco
    0.06
    describe
    0.06
    stashop
    0.06
    //$
    0.06
    encia
    0.06
    циклоп
    0.06
    Act Density 0.040%

    No Known Activations