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

    Neuronpedia

    INDEX
    Explanations

    * to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equated
    0.51
     trachea
    0.48
     homeostasis
    0.45
     décrit
    0.45
    sparsebundle
    0.44
    frid
    0.44
     Frid
    0.44
     cancers
    0.43
     ombil
    0.43
    ㈢
    0.43
    POSITIVE LOGITS
    the
    0.44
    dok
    0.41
    radle
    0.41
     上
    0.41
    Z
    0.40
    Dado
    0.40
    eko
    0.40
     gesto
    0.40
     noch
    0.39
    eken
    0.39
    Act Density 0.004%

    No Known Activations