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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isn
    -0.08
     préc
    -0.07
     wasn
    -0.06
     is
    -0.06
    Mod
    -0.06
    <r
    -0.06
     classy
    -0.06
     right
    -0.06
    ]];
    -0.06
     Isn
    -0.06
    POSITIVE LOGITS
    _sample
    0.08
    iqué
    0.07
    Companies
    0.07
    _date
    0.07
     đá
    0.07
    _male
    0.07
    WN
    0.07
    charged
    0.06
    UEL
    0.06
     deleteUser
    0.06
    Act Density 0.139%

    No Known Activations