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

    Neuronpedia

    INDEX
    Explanations

    -unit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Goal
    -0.07
    	Default
    -0.07
    Null
    -0.07
     progn
    -0.07
    Machine
    -0.07
     brass
    -0.06
     "#"
    -0.06
    <Comment
    -0.06
    ností
    -0.06
    _trip
    -0.06
    POSITIVE LOGITS
    رفته
    0.07
    ##_
    0.06
    .But
    0.06
    .precision
    0.05
    .Points
    0.05
    ,model
    0.05
    itt
    0.05
    .tell
    0.05
     menn
    0.05
    -CP
    0.05
    Act Density 0.022%

    No Known Activations