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

    Neuronpedia

    INDEX
    Explanations

    a, an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     issue
    -0.07
     projection
    -0.07
    ^.
    -0.07
    焦
    -0.07
    られる
    -0.07
    .rt
    -0.06
     modules
    -0.06
    paced
    -0.06
    TypeDef
    -0.06
     regions
    -0.06
    POSITIVE LOGITS
     hilarious
    0.07
    .setMaximum
    0.07
    ###↵↵
    0.06
    	sb
    0.06
     {}↵↵
    0.06
    _three
    0.06
     sergeant
    0.06
     ciudad
    0.06
    ////////////
    0.06
     +↵↵
    0.06
    Act Density 0.031%

    No Known Activations