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

    Neuronpedia

    INDEX
    Explanations

    parts of things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     kinda
    -0.06
     jednu
    -0.06
    	keys
    -0.06
    千
    -0.06
     Cedar
    -0.06
    Noise
    -0.06
     bài
    -0.06
    负责
    -0.06
     �
    -0.05
    POSITIVE LOGITS
    Instruction
    0.07
     Sources
    0.07
    _tensors
    0.07
     geom
    0.07
     photoc
    0.07
    .simpleButton
    0.06
     SOC
    0.06
    compress
    0.06
    _REPLY
    0.06
    lob
    0.06
    Act Density 0.063%

    No Known Activations