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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lic
    -0.07
    cent
    -0.07
     descri
    -0.06
     textColor
    -0.06
     tempor
    -0.06
     estr
    -0.06
     zkušen
    -0.06
    oria
    -0.06
    ीर
    -0.06
     vera
    -0.06
    POSITIVE LOGITS
    0.07
     olacağ
    0.07
     роз
    0.07
     шк
    0.07
    ,last
    0.07
     �
    0.07
     __
    0.07
    Bat
    0.07
    .While
    0.06
     sudden
    0.06
    Act Density 0.012%

    No Known Activations