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

    Neuronpedia

    INDEX
    Explanations

    short phrases and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    魷
    0.44
     drawable
    0.42
    ρός
    0.41
    prisoner
    0.40
     sicht
    0.38
    Յ
    0.38
    effici
    0.38
     prisoner
    0.38
     wicht
    0.37
    withtag
    0.37
    POSITIVE LOGITS
     Executive
    0.40
     An
    0.38
     Health
    0.38
     PC
    0.38
     Delta
    0.37
     Crohn
    0.37
     SR
    0.36
     Toggle
    0.36
     Authorities
    0.36
     Rural
    0.36
    Act Density 0.001%

    No Known Activations