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

    Neuronpedia

    INDEX
    Explanations

    latex code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hostage
    0.67
     aka
    0.63
     organ
    0.63
     stack
    0.62
     organs
    0.62
     Volks
    0.62
     AKA
    0.60
     casual
    0.60
     subsided
    0.60
     consolation
    0.60
    POSITIVE LOGITS
     %
    1.32
    %
    1.15
    %\
    1.11
     %\
    1.09
    %%
    1.07
    %%%%%%%%%%%%%%%%
    1.06
     %%
    1.06
     %[
    1.06
    %%%
    1.02
     %,
    1.01
    Act Density 0.003%

    No Known Activations