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

    Neuronpedia

    INDEX
    Explanations

    Data table entries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Baker
    -0.07
    fone
    -0.07
     الانتخاب
    -0.07
     Fence
    -0.07
    .Expressions
    -0.07
    	token
    -0.07
    إبراه
    -0.06
     apprec
    -0.06
    ᶘ
    -0.06
     ©
    -0.06
    POSITIVE LOGITS
    עות
    0.09
    ocols
    0.08
    ический
    0.07
    的效果
    0.07
    消
    0.07
     Shi
    0.07
    /ros
    0.07
     acids
    0.06
     insights
    0.06
    _WS
    0.06
    Act Density 0.009%

    No Known Activations