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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sexually
    -0.07
     chez
    -0.06
     Morris
    -0.06
    Photos
    -0.06
    -factor
    -0.06
    λου
    -0.06
     substitutions
    -0.06
    низ
    -0.06
     newcomers
    -0.06
    Production
    -0.06
    POSITIVE LOGITS
    idding
    0.07
     ()=>{↵
    0.06
    ज़
    0.06
     intptr
    0.06
    	Vk
    0.06
     资
    0.06
    	select
    0.06
    ấy
    0.06
    	AL
    0.06
     �
    0.06
    Act Density 0.028%

    No Known Activations