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

    Neuronpedia

    INDEX
    Explanations

    lick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stimulating
    -0.07
    ेस
    -0.07
    amine
    -0.07
    LP
    -0.06
    escription
    -0.06
     Reduction
    -0.06
    ysics
    -0.06
     estad
    -0.06
     completeness
    -0.06
     utility
    -0.06
    POSITIVE LOGITS
     francaise
    0.07
    شر
    0.06
    kont
    0.06
     �
    0.06
    opr
    0.06
     ngoài
    0.06
    ोकर
    0.06
     extortion
    0.06
     invading
    0.06
    予
    0.06
    Act Density 0.033%

    No Known Activations