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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #================================================================
    -0.07
    opoly
    -0.07
    bcm
    -0.06
     císa
    -0.06
    מ
    -0.06
    /(
    -0.06
     bringen
    -0.06
    stří
    -0.06
    _RM
    -0.06
     también
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.07
    two
    0.07
    Sketch
    0.07
    ++;
↵
    0.06
    ")
↵
    0.06
     Vlad
    0.06
    */↵
    0.06
    _virtual
    0.06
    ">↵↵↵
    0.06
    displayName
    0.06
    Act Density 0.000%

    No Known Activations