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

    Neuronpedia

    INDEX
    Explanations

    bangladesh, bangkok, bangalore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ʚ
    0.41
    ADIAN
    0.38
     dispar
    0.38
     czę
    0.38
    Stri
    0.38
    éges
    0.36
    Animal
    0.36
     delegations
    0.36
    損
    0.36
     Diana
    0.35
    POSITIVE LOGITS
     bang
    1.63
    Bang
    1.46
     Bang
    1.45
    bang
    1.37
     BANG
    1.34
     bangs
    1.16
    BANG
    1.12
     banged
    0.96
     banging
    0.95
    ladesh
    0.94
    Act Density 0.004%

    No Known Activations