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

    Neuronpedia

    INDEX
    Explanations

    increment or alternate sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     curved
    0.39
     headless
    0.38
     grained
    0.37
    lers
    0.36
    indigo
    0.36
    aranth
    0.36
    ປະກອບ
    0.35
    joon
    0.35
    แรก
    0.35
    insertCell
    0.35
    POSITIVE LOGITS
    trimenti
    0.38
     aumentando
    0.37
     increment
    0.36
     nächste
    0.35
    が進
    0.35
     гос
    0.35
     тему
    0.35
     volgende
    0.35
     поднима
    0.35
    Cheat
    0.35
    Act Density 0.029%

    No Known Activations