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

    Neuronpedia

    INDEX
    Explanations

    decoding text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gill
    0.42
     inputFile
    0.42
     send
    0.40
     strategically
    0.40
     SEND
    0.39
    发行
    0.39
     screenshots
    0.38
     sentencia
    0.38
    发送
    0.37
    ToSend
    0.37
    POSITIVE LOGITS
    constraintlayout
    0.38
    might
    0.38
    Decode
    0.37
    rover
    0.37
    Lucy
    0.37
     Vaz
    0.37
    Etiam
    0.36
    صار
    0.36
    삶
    0.36
    inet
    0.36
    Act Density 0.001%

    No Known Activations