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

    Neuronpedia

    INDEX
    Explanations

    billing and charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reinforcing
    0.40
    નમાં
    0.39
    留下
    0.39
    ົນ
    0.38
    0.38
     punctu
    0.38
    ☬
    0.38
    生活的
    0.37
    ături
    0.37
     stressing
    0.37
    POSITIVE LOGITS
    Goto
    0.46
    my
    0.43
    No
    0.43
    NO
    0.41
    те
    0.39
    Bs
    0.39
    ر
    0.39
     no
    0.38
    DA
    0.38
    고
    0.38
    Act Density 0.025%

    No Known Activations