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

    Neuronpedia

    INDEX
    Explanations

    substitute the value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Эк
    0.95
    縞
    0.81
    Phenyl
    0.79
     IMHO
    0.79
     Clamp
    0.79
     Attitudes
    0.78
     Opinions
    0.78
     LXXX
    0.77
     Exclusion
    0.77
     IMO
    0.77
    POSITIVE LOGITS
     dispuestos
    0.92
     geweld
    0.89
    包括
    0.84
     senang
    0.84
    ată
    0.82
     élég
    0.80
     présents
    0.80
     ayudan
    0.80
    oir
    0.80
    orang
    0.80
    Act Density 0.006%

    No Known Activations