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

    Neuronpedia

    INDEX
    Explanations

    Basic, information, text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     StringWriter
    -0.07
     nga
    -0.06
     Construct
    -0.06
     infamous
    -0.06
     wrongdoing
    -0.06
     válido
    -0.06
    fuse
    -0.06
    ційні
    -0.06
     Fraser
    -0.06
     всп
    -0.06
    POSITIVE LOGITS
    EMPL
    0.07
     풍
    0.07
     �
    0.06
     rides
    0.06
    proved
    0.06
     analyzes
    0.06
     molds
    0.06
    /mol
    0.06
    bars
    0.06
    衡
    0.06
    Act Density 0.000%

    No Known Activations